The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of
deep learning (DL). However, the latter faces various issues, including the lack of data or …

Existing studies for gait recognition are dominated by 2D representations like the silhouette
or skeleton of the human body in constrained scenes. However, humans live and walk in the …

Given an image with multiple people, our goal is to directly regress the pose and shape of all
the people as well as their relative depth. Inferring the depth of a person in an image …

In autonomous driving, a LiDAR-based object detector should perform reliably at different
geographic locations and under various weather conditions. While recent 3D detection …

Detectors trained with massive labeled data often exhibit dramatic performance degradation
in some particular scenarios with data distribution gap. To alleviate this problem of domain …

Abstract Domain Adaptation (DA) approaches achieved significant improvements in a wide
range of machine learning and computer vision tasks (ie, classification, detection, and …

We present Scan2CAD, a novel data-driven method that learns to align clean 3D CAD
models from a shape database to the noisy and incomplete geometry of a commodity RGB …

Modern 3D human pose estimation techniques rely on deep networks, which require large
amounts of training data. While weakly-supervised methods require less supervision, by …

This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an
optimal set of category-specific keypoints, along with their detectors to predict 3D keypoints …

In this paper, we propose the LiDAR Distillation to bridge the domain gap induced by
different LiDAR beams for 3D object detection. In many real-world applications, the LiDAR …